How to use Jupyter Notebook via JupyterHub @ 觀察筆記

In this tutorial, you will learn how to use Jupyter Notebook via JupyterHub, and run an example code.

Step 1: Install JupyterHub and open the Notebook server

JupyterHub can be installed from the QTS App Center.[gallery columns="1" size="large" ids="3659"]

Launch and log in to JupyterHub.[gallery columns="1" size="large" ids="3660"]

Click the switch from Off to "On" to start the Notebook server.[gallery columns="1" size="large" ids="3661"]

The interface will appear as following:

"Running": Check started instances

"Upload": Upload local files to the server

"New": Open a new Notebook, terminal or folder

"Admin": Switch to the admin page (administrator accounts only)

Sign out of Jupyter Notebook[gallery columns="1" size="large" ids="3662"]

If a Notebook is running, click "Running" to view the following page. You can also click "Shutdown" to close it.[gallery columns="1" size="large" ids="3663"]

Administrators can enter the ""Admin" page and access a user's Notebook.[gallery columns="1" size="large" ids="3664"]

Step 2: Run example code

Choose "Jupyter_example" on the list.[gallery columns="1" size="large" ids="3666"]

Open "example.ipynb".[gallery columns="1" size="large" ids="3667"]

A Python example code will be opened on a new Notebook.
This program can train a Convolutional Neural Network via Keras, which is a high-level neural networks API, for handwritten digit recognition in MNIST dataset.
For more information, visit:
Keras: https://keras.io/
MNIST: http://yann.lecun.com/exdb/mnist/[gallery columns="1" size="large" ids="3670"]

The example code has been executed and saved. You can also run it again.
- Click "Run" to execute a specific section or run it sequentially.[gallery columns="1" size="large" ids="3671"]
- Click "Cell" and choose "Run All" to execute complete code.[gallery columns="1" size="large" ids="3672"]
- For more Notebook tutorials, visit http://jupyter.org/documentation

The program does the following:
- At the beginning, required libraries are imported.
  Import Keras libraries[gallery columns="1" size="large" ids="3673"]
  
  Import other Python libraries
  
  [gallery columns="1" size="large" ids="3674"]
- Load MNIST dataset[gallery columns="1" size="large" ids="3675"]
  
  Randomly pick and check an image-label pair
  
  [gallery columns="1" size="large" ids="3676"]
- Preprocess the training set
  Reshape and normalize training images[gallery columns="1" size="large" ids="3677"]
  
  One-hot encode training labels
  
  [gallery columns="1" size="large" ids="3678"]
- Create a Sequential Model layer by layer[gallery columns="1" size="large" ids="3679"]
- Use the Adam optimizer and choose categorical cross entropy as the objective function to train the model. The following part runs for a few seconds.[gallery size="large" columns="1" ids="3680"]
- Evaluate the model using the test set. Although the accuracy on training set is higher than 99%, the accuracy on the test set may slightly decrease.[gallery columns="1" size="large" ids="3682"]
- Finally the testing results are displayed.[gallery columns="1" size="large" ids="3683"]